A Comparative Study of Convolutional Neural Network Architectures for Enhanced Tomato Leaf Disease Classification Using Refined Statistical Features
Bibliographic record
Abstract
Tomatoes, a staple in culinary practices, are currently in high demand yet low supply in India, rendering them unaffordable to the general population.This issue largely stems from the inability of farmers to identify and control prevalent tomato leaf diseases, leading to significant crop losses.Early detection and classification of leaf diseases are paramount to mitigate this problem, thereby boosting crop productivity.Despite extensive research in this domain, the precise localization and identification of various tomato leaf diseases present a complex task.This complexity arises from the significant overlap between the healthy and diseased portions of the leaves.The process is further complicated by the minimal contrast between the background and foreground of the specimen under investigation.To address these challenges, this study conducts a comprehensive performance analysis of several Convolutional Neural Networks (CNNs) models, namely, ResNet-152, ResNet-101, VGGNet, Alex Net, and LeNet, applied to the PlantVillage dataset.The results indicate that the ResNet-152 and ResNet-101 models yield superior accuracy rates when applied to both full-resolution source images and their background-removed counterparts.The performance outcomes reported herein surpass those documented in the existing literature, demonstrating the potential for significant advancements in the early detection and classification of tomato leaf diseases.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".